Semantic segmentation of kidneys and kidney tumors offers an expressive characterization of the lesion, but it imposes an even larger burden of manual effort than most nephrometry scores. A number of manual scoring systems, termed nephrometry scores, have been proposed for this purpose ( Kutikov and Uzzo, 2009 Ficarra et al., 2009 Simmons et al., 2010), but they have seen limited adoption due to the significant manual effort they require ( Simmons et al., 2012), the interobserver variability between expert raters ( Spaliviero et al., 2015), and their limited predictive power ( Kutikov et al., 2011 Hayn et al., 2011 Okhunov et al., 2011). Clinicians predominantly rely on imaging, primarily CT, to assess the complexity and aggression of renal masses. With these developments, there is an exciting opportunity to reduce overtreatment of renal tumors without compromising oncologic outcomes ( Mir et al., 2017), but there is a need for methods to objectively quantify the complexity and aggression of kidney tumors in order to better inform treatment decisions like radical nephrectomy vs. Further, a growing body of literature suggests that a large proportion of renal tumors are indolent ( Richard et al., 2016 Uzosike et al., 2018 McIntosh et al., 2018 Patel et al., 2016), meaning they will never become a danger to the patient, and thus active surveillance has emerged as an increasingly popular treatment strategy for tumors exhibiting less aggressive characteristics in imaging. However, in order to preserve renal function ( Scosyrev et al., 2014), partial nephrectomy, where only the tumor is removed, has recently become the standard of care in an increasing share of tumors with lower surgical complexity ( Campbell et al., 2017). Traditionally, kidney tumors were removed through radical nephrectomy in which the entire kidney along with the tumor are excised ( Robson, 1963). Surgical removal of localized RCC is regarded as curative ( Capitanio and Montorsi, 2016), so most localized kidney tumors are removed despite the sizable minority that are postoperatively found to be benign ( Kim et al., 2019). It is often difficult to radiographically differentiate between benign kidney tumors (e.g., angiomyolipoma and oncocytoma) and malignant Renal Cell Carcinoma (RCC) ( Millet et al., 2011), but most kidney tumors are eventually found to be malignant ( Chawla et al., 2006). The incidence of kidney tumors is increasing, especially for small, localized tumors that are often discovered incidentally ( Hollingsworth et al., 2006). This challenge has now entered an “open leaderboard” phase where it serves as a challenging benchmark in 3D semantic segmentation. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). These predictions were scored and ranked according to their average Sørensen-Dice coefficient between the kidney and tumor across all 90 cases. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private.
A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes.